Moss-Audio Captioning is a first of its kind! | Here's the repo: I modified the GUI to allow for batch captioning, youtube videos, and file chunking.

I personally think this is a a very cool app and truly something new. MOSS-Audio is a new open-source AI model designed to go far beyond basic speech transcription. It can listen to recordings, caption what is happening, detect sounds and events, analyze music, and even answer questions about the audio. Think of it a bit like Joy Caption, but for audio instead of images. Instead of only converting speech to text, it attempts to understand the entire sound environment. This makes it useful for po

More from StableDiffusion

Looneytunes background style for ZIT

StableDiffusion·4

Got early access access to LingBot-World-Fast at 17 FPS! Here's what I found.

StableDiffusion·5

Got early access access to LingBot-World-Fast at 17 FPS! Here's what I found.

StableDiffusion·6

Ernie VS Qwen and ZiT - Big Test

StableDiffusion·6

LTX 2.3 Prompt Relay with a messy zombie chase scene(Prompt Relay test)

StableDiffusion·8

Does anyone know why my Z-image base outputs are all this garbage? I'm using a Z-Image turbo workflow (works great with that model) and i swapped out the mode, Vae, text encoder, etc to Z-image base ones from the official sources, what else am i doing wrong?

StableDiffusion·6